opencode-skills-collection 4.0.53 → 4.0.55

package/bundled-skills/docs/users/skills-library-overview.md

@@ -1,87 +0,0 @@
-# The Full Skill Library: At-a-Glance Overview
-
-Agentic Awesome Skills ships a verified catalog of **2,107 skills** in `skills/<skill-id>/SKILL.md`. This page is a curated high-level map of the whole library: how skills are organized, the main capability areas and their approximate sizes, the risk labels you will encounter, and the authoritative surfaces to browse when you need the complete, current list.
-
-The authoritative, machine-generated catalog is [`CATALOG.md`](../../CATALOG.md). This overview is a hand-maintained index; it can lag the catalog after a release, so treat `CATALOG.md` and `skills_index.json` as the source of truth for counts and exact skill lists.
-
-## How the library is organized
-
-Every skill directory contains a `SKILL.md` whose frontmatter drives discovery:
-
-| Field | Purpose |
-| --- | --- |
-| `name` | Canonical skill id, e.g. `email-issue-fixer` |
-| `description` | Short purpose and trigger summary shown in search surfaces |
-| `category` | Thin grouping used by UI/search (see notes below) |
-| `tags` | Free-form keywords for search |
-| `risk` | One of `none`, `safe`, `critical`, `offensive`, or `unknown` |
-| `source` / `source_type` | Provenance of the skill content |
-| `date_added` | When the skill entered the registry |
-
-The full registry is exposed through three consistent surfaces:
-
-- [`CATALOG.md`](../../CATALOG.md) — human-readable catalog grouped by category.
-- `skills_index.json` — the legacy compatibility manifest (documented in [`discovery-manifest.md`](discovery-manifest.md)).
-- `data/catalog.json` — structured catalog used by the catalog app and AAS Core.
-
-> The `category` field is loose and historically fragmented (hundreds of skills are unclassified). Use `tags`, full-text search, and the AAS Core `search_skills` tool instead of relying on the category field as a taxonomy.
-
-## Capability areas
-
-The table below groups the real catalog data into editorial capability areas so you can find the region of the library that matches your task. Counts are approximate and change as the catalog evolves.
-
-| Capability area | Approx. skills | What you will find |
-| --- | ---: | --- |
-| Development & code quality | 480 | General, frontend, backend, mobile and fullstack development; language-specific guidance; code review and quality patterns |
-| Other & uncategorized | 330 | Small, niche, or legacy skills without a clean category label |
-| Cloud & infrastructure | 215 | Cloud platforms, DevOps, databases, operations, and ML infrastructure |
-| AI, agents & ML | 205 | Agent workflows, orchestration, evaluation, prompt engineering, and voice agents |
-| Automation, productivity & workflow | 190 | Task automation, workflows, browser automation, productivity, and collaboration |
-| Content, writing & creative | 160 | Writing, design, graphics, media, video, and presentation skills |
-| Business, product & research | 160 | Strategy, planning, product, project management, legal, finance, research, education, and health |
-| Security & pentesting | 85 | Security engineering, offensive testing, and defensive hardening |
-| Marketing, growth & SEO | 70 | Campaigns, analytics, SEO, growth, and app-store optimization |
-| Data & document processing | 65 | Data science, engineering, spreadsheets, documents, and knowledge management |
-| Testing & reliability | 55 | Test authoring, automation, reliability, and quality engineering |
-| Meta, authoring & special | 35 | Meta skills, skill authoring, and general-purpose helper skills |
-| API & integrations | 30 | Connectors and automation built around third-party APIs |
-| Gaming & blockchain | 25 | Game development, blockchain, and cryptocurrency |
-
-## Risk labels
-
-Every skill carries a `risk:` label in its frontmatter:
-
-| Risk | Meaning |
-| --- | --- |
-| `none` | No elevated risk; plain productivity guidance |
-| `safe` | Generally safe; local or low-impact operations |
-| `critical` | Privileged, destructive, or high-impact operations (code execution, deployments, pipelines) |
-| `offensive` | Offensive security / penetration-testing content; review the security guardrails before use |
-| `unknown` | Legacy or unclassified content that predates the risk-labeling scheme |
-
-Of the current catalog, roughly **1,090 are `critical`**, **850 are `safe`**, **100 are `none`**, and **60 are `offensive`**.
-
-Read [`SECURITY_GUARDRAILS.md`](../../docs/SECURITY_GUARDRAILS.md) and the [`security-guardrails`](../../docs/contributors/security-guardrails.md) contributor guide before invoking anything marked `critical` or `offensive`.
-
-## How to find the right skill
-
-1. **Search the full catalog** — with AAS Core running, use `search_skills`/`get_skill`; see the [usage guide](usage.md).
-2. **Browse the generated catalog** — [`CATALOG.md`](../../CATALOG.md) lists every skill by category with description, risk, source, and tags.
-3. **Use bundles as editorial shortlists** — see [bundles](bundles.md) for curated packs like the Web Wizard.
-4. **Use the tool-specific guides** — [Claude Code](claude-code-skills.md), [Codex CLI](codex-cli-skills.md), [Cursor](cursor-skills.md), and [Gemini CLI](gemini-cli-skills.md) include starter picks.
-
-## Distribution surfaces
-
-The same skills reach you through several channels, all backed by the same source tree:
-
-- **Full library** — direct install of the complete catalog (`~/.agents/skills/` by default).
-- **Plugins** — root and bundle plugins for Claude Code and Codex (see [plugins](plugins.md)).
-- **AAS Core** — agent-owned, reproducible selection validated against the catalog.
-
-## Related pages
-
-- [Usage guide](usage.md) — compose and use a skill stack.
-- [AAS Core](aas-core.md) — agent-owned catalog search and selection.
-- [Discovery manifest](discovery-manifest.md) — the machine-readable `skills_index.json` contract.
-- [Bundles](bundles.md) — curated skill packs.
-- [Security skills](security-skills.md) — guidance for security-relevant skills.

package/bundled-skills/docs/users/skills-vs-mcp-tools.md

@@ -1,108 +0,0 @@
-# Skills, AAS MCP, and Other MCP Tools
-
-The short version is:
-
-- **Skills** are reusable `SKILL.md` playbooks that tell an AI assistant how to execute a workflow.
-- **AAS MCP** is the local, read-only interface through which an agent retrieves the verified AAS catalog without ranking, inspects evidence, and records its exact selected IDs in a proposed stack.
-- **Other MCP tools** connect an assistant to external systems such as APIs, databases, browsers, or hosted services.
-- **The `aas` CLI** validates the durable project profile and agent-selected stack, then previews exact lifecycle operations under human control.
-
-These surfaces are complementary. AAS Core connects them around the approved `aas-stack.json` manifest.
-
-## What a skill does
-
-A skill gives the model better instructions for a repeated task such as:
-
-- planning a feature;
-- reviewing code;
-- running a security audit;
-- writing a README;
-- debugging a failing test suite.
-
-In practice, a skill improves the assistant's decision-making, structure, and process. It remains content, not an executable capability or a grant of authority.
-
-Examples:
-
-- `@brainstorming` helps the model clarify requirements before implementation.
-- `@lint-and-validate` helps the model run appropriate quality checks before claiming success.
-
-## What AAS MCP does
-
-AAS MCP is part of this repository's product, not an unrelated external integration. Codex or Claude uses it to call the same deterministic AAS Core that powers the CLI projections.
-
-It exposes exactly:
-
-- `search_skills`;
-- `get_skill`;
-- `compose_stack`;
-- `inspect_stack`;
-- `diff_stack`;
-- the `aas://skills/{id}` resource template.
-
-The agent inspects the project using its normal local capabilities, searches and reads the complete catalog, and chooses the exact skills. AAS MCP does not scan the repository itself, and Core does not rank or exclude candidates. Catalog metadata is informational only.
-
-AAS MCP is local stdio, process-per-session, read-only, offline-capable, and contains no model credentials or telemetry. Its tool calls do not install or remove skills, apply a stack, update catalogs, or edit host configuration.
-
-## What other MCP tools do
-
-An external MCP tool may give the model a capability it would not otherwise have, such as:
-
-- reading from a database;
-- calling GitHub APIs;
-- fetching documentation from a service;
-- creating calendar events;
-- querying or changing another system.
-
-Those tools expand what the assistant can do in the world. Their permissions, network behavior, and write boundaries depend on each server. They are different from the deliberately narrow AAS MCP catalog/composition boundary.
-
-## What the CLI does
-
-The `aas` CLI is the explicit operational interface for:
-
-- catalog status and updates;
-- MCP configuration;
-- validation and composition of an agent-selected stack;
-- manifest validation;
-- plan creation and read-only diagnostics.
-
-The durable artifact is `aas-stack.json`, which pins catalog identity, targets, the project profile, and exact skill IDs. The agent proposes it; the user reviews it. It has no Core selection policy. `stack validate` checks it, and `stack plan` creates an immutable preview bound to the observed managed state and exact operations.
-
-`stack apply` and `stack recover` exist only for controlled preview development. They are experimental, disabled by default, and are not supported or certified preview safety claims.
-
-## The easiest mental model
-
-- **Skills provide the operating guidance.**
-- **AAS MCP gives the agent complete catalog access and records the selection the agent makes.**
-- **`aas-stack.json` records what the user approved.**
-- **The CLI validates and previews the lifecycle.**
-- **Other MCP servers provide access to outside systems.**
-
-## Which path should you start with?
-
-Start with **AAS Core** when:
-
-- you use Codex or Claude with local MCP support;
-- you want the agent to compose a small stack from project evidence;
-- you need complete catalog access and a reproducible manifest of the agent's exact selection;
-- you want a reviewable plan before any skill changes.
-
-Start with a **direct skill or specialized plugin** when:
-
-- the host does not yet have a native AAS MCP configuration adapter;
-- you already know the exact skill or fixed domain pack you want;
-- you prefer manual invocation without a managed stack lifecycle.
-
-Add **other MCP tools** when the work needs live access to APIs, services, databases, or hosted platforms. A stack can contain skills that guide those integrations without granting the external permissions itself.
-
-## Preview limits
-
-AAS Core helps Codex and Claude search and read the complete local catalog, choose exact skill IDs, and preserve them in a reproducible stack. Metadata may be reported as unknown, but it is informational and never blocks selection or use. Apply and recovery remain experimental.
-
-## Good next reads
-
-- [AAS Core](aas-core.md)
-- [Getting Started](getting-started.md)
-- [FAQ](faq.md)
-- [Bundles](bundles.md)
-- [Workflows](workflows.md)
-- [Plugins for Claude Code and Codex](plugins.md)

package/bundled-skills/docs/users/specialized-plugin-roadmap.md

@@ -1,101 +0,0 @@
-# Specialized Plugin Roadmap
-
-This roadmap shifts Agentic Awesome Skills from "one giant plugin with every safe skill" toward a smaller set of focused, high-value Codex and Claude plugins.
-
-The full catalog remains useful as a repository and installer. The plugin product should be different: clear jobs, narrow install surfaces, strong names, and skill groups that users can trust without browsing 1,678 options.
-
-## Official Codex Basis
-
-The current Codex manual draws a useful line between skills and plugins:
-
-- Skills are the reusable workflow authoring format.
-- Plugins are the installable distribution unit for reusable skills, apps, MCP servers, and stable workflows.
-- Codex uses progressive disclosure for skills, but the initial skills list has a context budget. Very large installed sets can have shortened descriptions or omitted skills.
-- Plugin authors should build a plugin when they want to share a workflow across teams, bundle app integrations or MCP configuration, package hooks, or publish a stable package.
-
-That makes specialized plugins the better default product shape. A root plugin can exist for compatibility and advanced users, but it should not be the main recommendation.
-
-## Selection Method
-
-This snapshot pass evaluated the then-current local catalog. For current catalog checks, use the canonical root `skills_index.json` and treat `data/skills_index.json` only as the compatibility mirror:
-
-- Total skills evaluated in this snapshot: 1,678.
-- Broadest categories: development, cloud, AI/ML, security, business, workflow, content, marketing, automation, and web development.
-- Existing editorial bundles are all small and mostly plugin-compatible, which makes them a good starting point.
-- The stronger opportunity is to turn the best bundles into first-class product plugins with sharper names, richer descriptions, and optional app/MCP extensions.
-
-Candidate details live in `data/specialized-plugin-candidates.json`. Each listed skill ID exists in the catalog and was checked as Codex-supported.
-
-The candidates are now enabled as editorial bundle plugins. Running `npm run bundles:sync` materializes them under `plugins/agentic-bundle-aas-*`, adds Codex marketplace entries in `.agents/plugins/marketplace.json`, adds Claude marketplace entries in `.claude-plugin/marketplace.json`, and refreshes `docs/users/bundles.md`.
-
-## Tier 1 Plugins
-
-These should become the primary marketplace surface.
-
-| Plugin | Job | Why it deserves focus |
-| --- | --- | --- |
-| AAS Web App Builder | Build modern React/Next.js web apps. | High-demand, coherent path from UI design to implementation, forms, Tailwind, and SEO. |
-| AAS Product Design Studio | Create richer UI, brand, motion, 3D, and visual assets. | Stronger than a generic design bundle; it has a clear creative/product promise. |
-| AAS Security Engineer | Run authorized testing, audit, and hardening workflows. | Security is deep enough to justify a standalone plugin with explicit boundaries. |
-| AAS Secure App Builder | Build secure application features. | Keeps defensive implementation separate from offensive assessment. |
-| AAS Documents & Presentations | Create, edit, convert, and automate DOCX/XLSX/PPTX/PDF/Google files. | Concrete productivity plugin with obvious user value and room for app integrations. |
-| AAS Data Analytics | Track, query, visualize, dashboard, and experiment. | Data workflows need a repeatable toolchain, not one isolated skill. |
-| AAS Agent & MCP Builder | Build agentic apps, MCP tools, RAG, and eval loops. | Maps directly to plugin-based agent workflows because it can grow into MCP config. |
-| AAS QA & Test Automation | Write, debug, stabilize, and scale tests. | Testing is a workflow chain: TDD, browser automation, failure diagnosis, and regression prevention. |
-| AAS DevOps & Cloud | Ship infrastructure, deployment, and operational workflows. | Strong fit for scripts, deployment gates, incident practice, and cloud patterns. |
-| AAS Accessibility & Inclusive UX | Audit, test, and fix accessible product experiences. | Accessibility is a standalone product-quality workflow across audit, automated scans, screen readers, fixes, and QA. |
-| AAS API Platform Builder | Design language-agnostic API platforms. | Complements Python API Builder with OpenAPI, auth, security, documentation, load testing, and observability. |
-| AAS SaaS Launch & Revenue | Launch, price, monetize, measure, and grow SaaS products. | Turns startup, pricing, payments, analytics, lifecycle, referral, and SEO skills into one revenue workflow. |
-| AAS AI Product & Evaluation Ops | Define, evaluate, instrument, and improve AI product features. | Covers the PM/product side of AI: metrics, evals, tracing, experiments, model evaluation, and context constraints. |
-
-## Tier 2 Plugins
-
-These are promising and should be hardened after Tier 1.
-
-| Plugin | Job | Why it is promising |
-| --- | --- | --- |
-| AAS Marketing, SEO & Growth | Plan, write, measure, and improve acquisition work. | Better as a growth workflow than many isolated copy/SEO skills. |
-| AAS Automation Builder | Design durable automations across tools. | Can become much stronger when paired with apps and MCP configuration. |
-| AAS Observability IR | Monitor systems, debug production, and write postmortems. | Operational work benefits from consistent proof gates. |
-| AAS Python API Builder | Build Python APIs and services with tests. | Language-specialized plugin with practical framework coverage. |
-| AAS Mobile App Builder | Ship Expo, React Native, Flutter, and iOS apps. | Covers architecture, release, CI, native platforms, and store optimization. |
-| AAS Data Engineering Platform | Build pipelines, transforms, warehouses, embeddings, and RAG-ready data foundations. | Connects analytics engineering, data pipelines, vector databases, and AI data foundations. |
-| AAS Privacy & Compliance Engineering | Engineer privacy and compliance controls. | Uses existing GDPR, PCI, privacy-by-design, compliance, spec, and security review skills without inventing new skills. |
-| AAS Localization & International Growth | Expand products across languages and markets. | Combines existing i18n, hreflang, SEO, content, copy, analytics, and market research skills. |
-
-## Recommended Product Changes
-
-1. Keep the root plugin as an advanced "full plugin-safe library" path.
-2. Make specialized plugins the default recommendation in README, docs, and marketplace ordering.
-3. Rename or reframe bundle plugins as product plugins where the job is clear.
-4. Add richer `interface` metadata to the strongest plugin manifests: display name, short description, brand color, and default prompt.
-5. Add per-plugin quality gates:
-  - every skill exists in canonical `skills_index.json`;
-   - every skill is Codex-supported before Codex publication;
-   - every skill is Claude-supported before Claude publication;
-   - every plugin has a 5-10 skill target range unless it has a concrete reason to be larger;
-   - every plugin description says who it is for, what it helps do, and what it does not cover.
-6. Move social and launch messaging from daily individual skills to plugin stories:
-   - "Web App Builder: from design to tested Next.js app";
-   - "Documents & Presentations: DOCX/PPTX/XLSX/PDF without manual file surgery";
-   - "OSS Maintainer: PR review, changelog, release, and contributor handoff".
-
-## What Not To Do
-
-- Do not present the root plugin as the best default for new users.
-- Do not create plugin names that are just categories, such as "development" or "cloud".
-- Do not publish large plugins whose only promise is "more skills".
-- Do not mix offensive security, defensive app security, and general code review into one vague security plugin.
-- Do not treat a bundle as good enough merely because all included skills are compatible.
-
-## Implementation Status
-
-Implemented in the repository:
-
-- `data/editorial-bundles.json` includes all 22 specialized plugin candidates.
-- `data/specialized-plugin-candidates.json` remains the source-of-truth shortlist and rationale.
-- `plugins/agentic-bundle-aas-*` contains the generated plugin folders.
-- `.agents/plugins/marketplace.json` and `.claude-plugin/marketplace.json` expose the generated plugin entries.
-- `docs/users/bundles.md` renders the specialized plugin sections for users.
-
-Future improvements should focus on brand metadata, optional MCP/app integrations where a plugin naturally needs live tools, and keeping every plugin backed by existing canonical skills.